> ## Documentation Index
> Fetch the complete documentation index at: https://docs.poixe.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Nano Banana Image Generation

Nano Banana is Google's family of Gemini AI image generation models. It supports generating and editing images conversationally using text, images, or a combination of both.

The family includes three main models:

| Model alias | Official model name | Positioning |
| - | - | - |
| `nano-banana` | `gemini-2.5-flash-image` | Speed first: high throughput, low latency |
| `nano-banana-pro` | `gemini-3-pro-image-preview` | Quality first: supports 4K and advanced text rendering |
| `nano-banana-2` | `gemini-3.1-flash-image-preview` | Optimized for speed and large-scale usage |

<Callout type="info" icon="info-circle">
  Poixe supports calling models by either **model alias** or **official native model name**.
  Aliases are only internal mappings. If the official models are later updated or replaced, we may adjust the alias mappings accordingly to keep them working.
</Callout>

## Showcase

Nano Banana excels at text rendering, complex compositions, and understanding Eastern aesthetics.

<Tabs>
  <Tab title="Along the River During the Qingming Festival">
    <img src="https://mintcdn.com/terobox/6ZjcmaCT7UvKUscl/assets/images/nano-banana-old-bridge.png?fit=max&auto=format&n=6ZjcmaCT7UvKUscl&q=85&s=5b43db106667d0ddd3499d9aa1a7b4ab" alt="nano banana old bridge" width="1280" height="543" data-path="assets/images/nano-banana-old-bridge.png" />
  </Tab>

  <Tab title="Movie Storyboard">
    <img src="https://mintcdn.com/terobox/6ZjcmaCT7UvKUscl/assets/images/nano-banana-movies.png?fit=max&auto=format&n=6ZjcmaCT7UvKUscl&q=85&s=79b1c051e7204049905a7d5ee5d1733a" alt="nano banana movies" width="1536" height="2752" data-path="assets/images/nano-banana-movies.png" />
  </Tab>

  <Tab title="Acrylic Board">
    <img src="https://mintcdn.com/terobox/6ZjcmaCT7UvKUscl/assets/images/nano-banana-card.png?fit=max&auto=format&n=6ZjcmaCT7UvKUscl&q=85&s=f21a96acd649e96181667c8bdf34ba89" alt="nano banana acrylic board" width="765" height="1024" data-path="assets/images/nano-banana-card.png" />
  </Tab>

  <Tab title="Group Photo">
    <img src="https://mintcdn.com/terobox/6ZjcmaCT7UvKUscl/assets/images/nano-banana-pose.png?fit=max&auto=format&n=6ZjcmaCT7UvKUscl&q=85&s=41f9ef77fc3a3106440f177319048164" alt="nano banana acrylic board" width="1080" height="1080" data-path="assets/images/nano-banana-pose.png" />
  </Tab>

  <Tab title="Douyin Screenshot">
    <img src="https://mintcdn.com/terobox/6ZjcmaCT7UvKUscl/assets/images/nano-banana-douyin.png?fit=max&auto=format&n=6ZjcmaCT7UvKUscl&q=85&s=663ffbad7c01094fd0426197ff380d6e" alt="nano banana douyin" width="768" height="1376" data-path="assets/images/nano-banana-douyin.png" />
  </Tab>

  <Tab title="Facial Expressions">
    <img src="https://mintcdn.com/terobox/6ZjcmaCT7UvKUscl/assets/images/nano-banana-emoticon.png?fit=max&auto=format&n=6ZjcmaCT7UvKUscl&q=85&s=bc9e3c604eea389a34d02f20a0dcc1b5" alt="nano banana emoticon" width="1472" height="1133" data-path="assets/images/nano-banana-emoticon.png" />
  </Tab>

  <Tab title="Fashion Portrait">
    <img src="https://mintcdn.com/terobox/6ZjcmaCT7UvKUscl/assets/images/nano-banana-fashion.png?fit=max&auto=format&n=6ZjcmaCT7UvKUscl&q=85&s=d21124d4a9a8e552bc160427f9f385bb" alt="nano banana fashion" width="2286" height="4096" data-path="assets/images/nano-banana-fashion.png" />
  </Tab>

  <Tab title="Makeup Analysis">
    <img src="https://mintcdn.com/terobox/6ZjcmaCT7UvKUscl/assets/images/nano-banana-makeup.png?fit=max&auto=format&n=6ZjcmaCT7UvKUscl&q=85&s=43c3dd833db9369687fb1e162d7fdc7e" alt="nano banana makeup" width="1106" height="1943" data-path="assets/images/nano-banana-makeup.png" />
  </Tab>

  <Tab title="Movie Poster">
    <img src="https://mintcdn.com/terobox/6ZjcmaCT7UvKUscl/assets/images/nano-banana-poster.png?fit=max&auto=format&n=6ZjcmaCT7UvKUscl&q=85&s=8caa490b83bd92cd1d18bcf4c638dd36" alt="nano banana poster" width="832" height="1248" data-path="assets/images/nano-banana-poster.png" />
  </Tab>
</Tabs>

## Model comparison

| Feature | Nano Banana | Nano Banana Pro | Nano Banana 2 |
| - | - | - | - |
| Generation speed | \~10 s | \~20 s | \~8 s |
| Max resolution | 1024×1024 (1K) | 4096×4096 (4K) | 4096×4096 (4K) |
| Text rendering | Basic | Excellent | Good |
| Reference images | Up to 3 | Up to 14 | Up to 14 |
| Reasoning | Standard | Advanced | Standard+ |
| Local editing | Basic | Advanced | Intermediate |

**Recommendations**:

* Fast image output, general scenarios → `nano-banana`
* High clarity, text rendering, professional design → `nano-banana-pro`
* Lower cost and higher concurrency → `nano-banana-2`

## Pricing

The Nano Banana family follows Google's official billing logic, and also benefits from Poixe's user-level discounts.

Base billing has three parts: prompt input (Text/Image Input), text/thinking output (Text Output), and image generation output (Image Output).

<Tabs>
  <Tab title="Nano Banana">
    Corresponds to `nano-banana` or `gemini-2.5-flash-image`:

    * **Input (text/image)**: \$0.30 / 1M Tokens
    * **Output (text)**: \$2.50 / 1M Tokens
    * **Output (image)**: \$30.00 / 1M Tokens
    * **Per-image price**: a standard image (1024x1024) consumes 1,290 tokens, about **\$0.039/image**.
  </Tab>

  <Tab title="Nano Banana Pro">
    Corresponds to `nano-banana-pro` or `gemini-3-pro-image-preview`:

    * **Input (text/image)**: \$2.00 / 1M Tokens
    * **Output (text/thinking)**: \$12.00 / 1M Tokens
    * **Output (image)**: \$120.00 / 1M Tokens
    * **Per-image price**:
      * **1K/2K resolution**: consumes 1,120 tokens, about **\$0.134/image**
      * **4K resolution**: consumes 2,000 tokens, about **\$0.240/image**
  </Tab>

  <Tab title="Nano Banana 2">
    Corresponds to `nano-banana-2` or `gemini-3.1-flash-image-preview`:

    * **Input**: \$0.5 / 1M Tokens
    * **Output (text)**: \$3.00 / 1M Tokens
    * **Output (image)**: \$60.00 / 1M Tokens
    * **Per-image price**:
      * **0.5K resolution**: consumes 747 tokens, about **\$0.045/image**
      * **1K resolution**: consumes 1,120 tokens, about **\$0.067/image**
      * **2K resolution**: consumes 1,680 tokens, about **\$0.101/image**
      * **4K resolution**: consumes 2,520 tokens, about **\$0.151/image**
  </Tab>
</Tabs>

<Callout type="info" icon="info-circle">
  **Note**: The above is only the official pricing. The final price on Poixe is calculated from these official prices with a discount based on your benefit level (Level).
</Callout>

## Quickstart

Poixe serves the Nano Banana models through the **Google Gemini Content protocol**, which is also the officially recommended way to call them. See the following documentation for details:

<CardGroup cols={1}>
  <Card title="Google Gemini Content Protocol" href="/en/api-reference/text-api/google-gemini-content/overview">
    Learn how to call the Nano Banana models through this protocol
  </Card>
</CardGroup>

<Callout type="info" icon="info-circle">
  **Note**: Because Nano Banana models involve image generation, response times are usually longer. We recommend using the secondary endpoint, which is friendlier to long-lived connections without a CDN. For configuration, see [Base URL](/en/api-reference/introduction/base-url).

  If your connection is unexpectedly interrupted during a call, see [Recovering Interrupted Responses](/en/api-reference/system-api/recoveries/overview) for how to use Poixe's recovery mechanism to continue retrieving the unfinished response.
</Callout>

### Request example

```bash theme={"theme":{"light":"min-light","dark":"min-dark"}}
curl "https://api.poixe.com/v1beta/models/gemini-3-pro-image-preview:generateContent" \
  -H "x-goog-api-key: $POIXE_API_KEY" \
  -H "Content-Type: application/json" \
  -X POST \
  -d '{
    "contents": [
      {
        "parts": [
          {
            "text": "An orange tabby cat sitting on a windowsill watching the rain, cyberpunk style"
          }
        ]
      }
    ],
    "generationConfig": {
      "responseModalities": ["Text", "Image"],
      "imageConfig": {
        "aspectRatio": "16:9",
        "imageSize": "2K"
      }
    }
  }'
```

### Response example

```json theme={"theme":{"light":"min-light","dark":"min-dark"}}
{
  "candidates": [
    {
      "content": {
        "parts": [
          {
            "text": "Here is a cyberpunk-style image of an orange tabby cat sitting on a windowsill watching the rain."
          },
          {
            "inlineData": {
              "mimeType": "image/png",
              "data": "iVBORw0KGgoAAAANSUhEUgAA..."
            },
            "thoughtSignature": "EtORtgIKzpG2Ag..."
          }
        ],
        "role": "model"
      },
      "finishReason": "STOP",
      "index": 0
    }
  ],
  "usageMetadata": {
    "promptTokenCount": 14,
    "candidatesTokenCount": 1253,
    "totalTokenCount": 1490,
    "promptTokensDetails": [
      {
        "modality": "TEXT",
        "tokenCount": 14
      }
    ],
    "candidatesTokensDetails": [
      {
        "modality": "IMAGE",
        "tokenCount": 1120
      }
    ],
    "thoughtsTokenCount": 223
  },
  "modelVersion": "gemini-3-pro-image-preview",
  "responseId": "cKaFae-1Ee307M8Py5OosAE"
}
```

### Output preview

Image data is returned base64-encoded. Decode it to get a PNG/JPEG image.

<img src="https://mintcdn.com/terobox/6ZjcmaCT7UvKUscl/assets/images/nano-banana-pro-output.png?fit=max&auto=format&n=6ZjcmaCT7UvKUscl&q=85&s=064d59c3056521de1ecef366a3a82dbe" alt="nano banana pro output" width="2752" height="1536" data-path="assets/images/nano-banana-pro-output.png" />

<Callout type="info" icon="info-circle">
  You can decode the base64 image data with an online tool (such as [Base64 Image Viewer](https://base64-image-viewer.poixe.com/)) or programmatically.
</Callout>

## Parameters

### Output type

Use `responseModalities` to control what is returned:

```json theme={"theme":{"light":"min-light","dark":"min-dark"}}
{
  "generationConfig": {
    "responseModalities": ["Image"] // Return only the image, no text
  }
}
```

Supported values: `Text`, `Image`

### Aspect ratio

Use `imageConfig.aspectRatio` to set the frame:

```json theme={"theme":{"light":"min-light","dark":"min-dark"}}
{
  "generationConfig": {
    "imageConfig": {
      "aspectRatio": "16:9" // Set the aspect ratio to 16:9
    }
  }
}
```

Supported aspect ratios: `1:1`, `2:3`, `3:2`, `3:4`, `4:3`, `4:5`, `5:4`, `9:16`, `16:9`, `21:9`

### Resolution

Supported output resolutions:

```json theme={"theme":{"light":"min-light","dark":"min-dark"}}
{
  "generationConfig": {
    "imageConfig": {
      "aspectRatio": "16:9",
      "imageSize": "4K" // Set the resolution to 4K
    }
  }
}
```

Supported resolutions: `1K` (1024x1024), `2K` (2048x2048), `4K` (4096x4096)

## Nano Banana Pro exclusive features

`nano-banana-pro` (`gemini-3-pro-image-preview`) offers the following advanced features:

* **4K HD output**: supports three resolution levels: 1K/2K/4K
* **Advanced text rendering**: suited for infographics, menus, marketing assets, and similar scenarios
* **Thinking mode**: the model first generates draft concept images, then outputs the final high-quality image
* **Multi-reference blending**: supports up to 14 reference images (including 6 high-fidelity object images + 5 person images)
* **Google Search grounding**: generate images based on real-time data (weather, stocks, etc.)

## Nano Banana 2 exclusive features

`nano-banana-2` (`gemini-3.1-flash-image-preview`) delivers high-quality image generation and conversational editing at a mainstream price, with lower latency and higher throughput. It is an efficient counterpart to `nano-banana-pro`, optimized for speed-sensitive and high-concurrency scenarios.

**Key updates:**

* **New resolution options**: supports `0.5K / 1K / 2K / 4K` (default 1K)
* **Enhanced real-time search**: combines text and image search results to give generation real-time information
* **Controllable thinking mode**: the thinking phase can be turned on or off
* **New aspect ratios**: supports `1:4`, `4:1`, `1:8`, `8:1`
* **Better aspect ratio adherence**: output framing is more stable
* **Improved image quality and consistency**
* **Improved multilingual text rendering (i18n)**

## Limitations

* Best-supported languages: English, Chinese, Japanese, Korean, French, German, Spanish, and other major languages
* Audio and video input are not supported
* All generated images include a [SynthID watermark](https://ai.google.dev/responsible/docs/safeguards/synthid?hl=zh-cn)
* Text rendering tip: first have the model generate the text content, then ask it to generate an image containing that text

## Using a client

We recommend [Cherry Studio](/en/use-cases/chat/cherry-studio). When configuring the model provider, choose the [Google Gemini native protocol](/en/api-reference/text-api/google-gemini-content/overview).

## Prompt resources

<CardGroup cols={2}>
  <Card title="Awesome Nano Banana Images" href="https://github.com/PicoTrex/Awesome-Nano-Banana-images">
    Community-curated prompts and generation examples
  </Card>

  <Card title="Nano Banana Hackathon Kit" href="https://github.com/google-gemini/nano-banana-hackathon-kit">
    Google's official Hackathon toolkit
  </Card>
</CardGroup>

## FAQ

<AccordionGroup>
  <Accordion title="Which version should I choose?">
    * Fast image output, general scenarios → `nano-banana` or `gemini-2.5-flash-image`
    * HD output, text rendering, professional design → `nano-banana-pro` or `gemini-3-pro-image-preview`
    * High-concurrency batch generation or cost-sensitive scenarios → `nano-banana-2` or `gemini-3.1-flash-image-preview`
  </Accordion>

  <Accordion title="What is the difference between nano-banana and gemini-2.5-flash-image?">
    None. `nano-banana` is an alias mapping within Poixe; the model actually called is
    `gemini-2.5-flash-image`.

    Likewise, `nano-banana-pro` maps to `gemini-3-pro-image-preview`, and they are the same model.

    For stability, we recommend using the official model names directly.
  </Accordion>

  <Accordion title="What format are the generated images?">
    Images are returned as base64-encoded data, usually PNG or JPEG, ready to use once decoded.
  </Accordion>

  <Accordion title="Is image editing supported?">
    Yes. You can upload images and edit them conversationally. Nano Banana Pro has stronger local editing capabilities.
  </Accordion>

  <Accordion title="Why does the number of generated images not match my request?">
    The model does not always generate exactly the number of images requested. This is a known limitation of the model.
  </Accordion>
</AccordionGroup>

## Related links

* [Google Gemini image generation documentation](https://ai.google.dev/gemini-api/docs/image-generation?hl=zh-cn)
* [Nano Banana official pricing](https://ai.google.dev/gemini-api/docs/pricing?hl=zh-cn#gemini-2.5-flash-image)
* [Nano Banana Pro official pricing](https://ai.google.dev/gemini-api/docs/pricing?hl=zh-cn#gemini-3-pro-image-preview)
* [Nano Banana 2 official pricing](https://ai.google.dev/gemini-api/docs/pricing?hl=zh-cn#gemini-3.1-flash-image-preview)
* [Google Gemini Content API Protocol](/en/api-reference/text-api/google-gemini-content/overview)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.